Latest AI JobsBrowse Jobs
pragmatike logo

Principal ML Ops Engineer (EMEA Remote)

pragmatikeUkraineWork with our Clients
Apply on company site
Salary
Not listed
Job type
Full-time
Work mode
Remote
Experience
Senior · 4+ yrs
Posted
23 Sept 2026
Status
Open · checked 9d ago

About this role

Fully remote in the EMEA timezone, this role is open to candidates seeking a technical position focused on building scalable machine learning inference platforms. The position suits an experienced infrastructure specialist with a strong background in production-grade model serving and distributed GPU systems.

Role Overview

Pragmatike is recruiting a Principal ML Ops Engineer for a well-funded distributed cloud infrastructure startup building AI-native cloud services. The position involves designing and operating core infrastructure to serve machine learning models at scale with high availability and low latency.

Key Responsibilities

Build and operate production-grade model serving infrastructure using tools like vLLM, TGI, or Triton
Design and implement deployment pipelines utilizing canary and blue/green rollout strategies
Develop auto-scaling systems, intelligent request routing layers, and multi-model serving architectures
Optimize network throughput, memory efficiency, model storage performance, and GPU utilization
Create observability systems to monitor inference latency, GPU usage, throughput, system health, and costs
Maintain CI/CD pipelines and model registries for reproducible and automated deployments
Manage the full lifecycle of machine learning systems, providing operational support and handling on-call duties
Establish engineering standards and contribute to platform scalability

Requirements

Four or more years of experience in SRE, platform engineering, ML Ops, or related infrastructure roles focused on machine learning systems
Practical experience using model serving frameworks such as Triton, TGI, or vLLM
Background in container orchestration and running GPU workloads in production environments
Familiarity with MLOps tooling, including automated deployment pipelines, experiment tracking, and model registries
Knowledge of Python and infrastructure-as-code technologies like Terraform or Helm
Understanding of distributed systems, production reliability, and performance optimization
Familiarity with utilizing AI coding assistants to speed up debugging and development
Independent working style suited to a remote-first environment

Nice to Have

Experience working with ML platforms such as MLflow, Kubeflow, or KubeAI
Understanding of multi-tenant inference systems, CUDA or ROCm optimization, and GPU scheduling
Background in cost optimization for various GPU types and inference tasks
Previous work in early-stage startups or greenfield infrastructure initiatives
Track record of constructing production systems from the ground up rather than supporting legacy platforms

Skills and Tools

Python
Terraform
Helm
vLLM
TGI
Triton
Kubeflow
MLflow
KubeAI
CUDA
ROCm

About the Company

Pragmatike acts as a recruitment partner for a well-funded, fast-scaling distributed cloud infrastructure startup that creates European deep-tech SaaS and AI-native cloud services. The organization delivers GPU-powered infrastructure for machine learning workloads, high-speed data transfer, and secure storage through a decentralized architecture designed to lower environmental impact.

How to Apply

Interested candidates should apply directly on the official company careers page.

Skills and tech stack

PythonTerraformHelmvLLMTGITritonKubeflowMLflowKubeAICUDAROCmMLOpsMachine LearningDistributed Systems

Questions candidates ask

What is the location of the position?

The position is fully remote within the EMEA timezone.

How many years of experience are required?

Candidates must have at least four years of experience in ML Ops, Platform Engineering, SRE, or similar infrastructure roles focused on machine learning systems.

What programming languages and tools are expected?

Proficiency in Python and infrastructure-as-code tools such as Terraform or Helm is required, along with experience using model serving frameworks like vLLM, TGI, or Triton.

What type of company is hiring?

Pragmatike is recruiting on behalf of a well-funded, fast-scaling distributed cloud infrastructure startup focused on European deep-tech SaaS and AI-native cloud services.

Are there on-call responsibilities?

Yes, the role includes owning the full lifecycle of machine learning systems, which involves operational support and on-call duties.

Ready to apply?

The application is on the official pragmatike careers page.

Apply on company site